PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Clouds

TL;DR

PCAM introduces a novel neural network architecture that uses the product of cross-attention matrices to improve point cloud registration by effectively combining geometric and contextual information for better correspondence matching.

Contribution

The paper presents PCAM, a new deep learning method utilizing cross-attention matrix products for joint correspondence finding and filtering in point cloud registration.

Findings

Achieves state-of-the-art results on registration benchmarks.

Effectively combines geometric and contextual features.

Outperforms previous deep learning approaches.

Abstract

Rigid registration of point clouds with partial overlaps is a longstanding problem usually solved in two steps: (a) finding correspondences between the point clouds; (b) filtering these correspondences to keep only the most reliable ones to estimate the transformation. Recently, several deep nets have been proposed to solve these steps jointly. We built upon these works and propose PCAM: a neural network whose key element is a pointwise product of cross-attention matrices that permits to mix both low-level geometric and high-level contextual information to find point correspondences. These cross-attention matrices also permits the exchange of context information between the point clouds, at each layer, allowing the network construct better matching features within the overlapping regions. The experiments show that PCAM achieves state-of-the-art results among methods which, like us, solve steps (a) and (b) jointly via deepnets. Our code and trained models are available at https://github.com/valeoai/PCAM.